{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/data/pufanyi/anaconda3/anacondabin/envs/live_bench/lib/python3.12/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n"
     ]
    }
   ],
   "source": [
    "import datasets\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "data = datasets.load_dataset(\"lmms-lab/LiveBench\", \"2024-09\", split=\"test\")\n",
    "\n",
    "\n",
    "def get():\n",
    "    for item in data:\n",
    "        if item[\"subtask\"] == \"Concrete Recognition\":\n",
    "            item[\"subtask\"] = \"Concrete Recognition\"\n",
    "        yield item"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Generating train split: 200 examples [01:38,  2.03 examples/s]\n"
     ]
    }
   ],
   "source": [
    "new_data = datasets.Dataset.from_generator(get, features=data.features)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Map: 100%|██████████| 200/200 [00:00<00:00, 364.40 examples/s]it/s]\n",
      "Creating parquet from Arrow format: 100%|██████████| 2/2 [00:00<00:00,  3.45ba/s]\n",
      "Uploading the dataset shards: 100%|██████████| 1/1 [00:17<00:00, 17.75s/it]\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "CommitInfo(commit_url='https://huggingface.co/datasets/lmms-lab/LiveBench/commit/e8be87798d7db2e22ee3b5aeedf16e2a460ac7b3', commit_message='Upload dataset', commit_description='', oid='e8be87798d7db2e22ee3b5aeedf16e2a460ac7b3', pr_url=None, repo_url=RepoUrl('https://huggingface.co/datasets/lmms-lab/LiveBench', endpoint='https://huggingface.co', repo_type='dataset', repo_id='lmms-lab/LiveBench'), pr_revision=None, pr_num=None)"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_data.push_to_hub(\"lmms-lab/LiveBench\", \"2024-09\", split=\"test\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "live_bench",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}